List files and directories in a remote path via SFTP.
AI agents call ssh_list_files to retrieve information from Claude Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs directory listing via SFTP, which is a non-destructive query operation. It retrieves information about files and directories on a remote server without creating, modifying, or deleting any data. The blast radius is minimal—the only risk is information disclosure about the remote filesystem structure, and even that requires the user to already have SSH access to the server.
From the tool's definition Tool name 'ssh_list_files' and description 'List files and directories in a remote path via SFTP' indicate a read-only operation that retrieves directory contents without modifying data.
Attacks that exploit this kind of access
List files and directories in a remote path via SFTP. It is categorised as a Read tool in the Claude Ssh MCP Server, which means it retrieves data without modifying state.
Register the Claude Ssh MCP server in PolicyLayer and add a rule for ssh_list_files: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Ssh. Nothing to install.
ssh_list_files is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ssh_list_files rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for ssh_list_files. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ssh_list_files is provided by the Claude Ssh MCP server (marabank/mcp-ssh-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →